ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations

Liu, Quan; Gaeta, Isabella; Zhao, Mengyang; Deng, Ruining; Jha, Aadarsh; Millis, Bryan A.; Mahadevan‐Jansen, Anita; Tyska, Matthew J.; Huo, Yuankai

doi:10.48550/arxiv.2101.00567

Cited by 1 publication

(1 citation statement)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [25], each pixel in a 2D video sequence was encoded to a high-dimensional embedding vector with the intuition that all pixels from the same cell, across spatial and temporal, should have the same feature representation (embedding). The renown cosine similarity [14,15] approach is commonly used to measure the similarities of any two pixels. For instance, A was the embedding vector of pixel a, and B was the embedding vector of pixel b.…”

Section: Cosine Embedding Based Instance Segmentation and Trackingmentioning

confidence: 99%

VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning

Zhao¹,

Liu²,

Jha³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recent advances in bioimaging have provided scientists a superior high spatial-temporal resolution to observe dynamics of living cells as 3D volumetric videos. Unfortunately, the 3D biomedical video analysis is lagging, impeded by resource insensitive human curation using off-the-shelf 3D analytic tools. Herein, biologists often need to discard a considerable amount of rich 3D spatial information by compromising on 2D analysis via maximum intensity projection. Recently, pixel embedding based cell instance segmentation and tracking provided a neat and generalizable computing paradigm for understanding cellular dynamics. In this work, we propose a novel spatial-temporal voxel-embedding (VoxelEmbed) based learning method to perform simultaneous cell instance segmenting and tracking on 3D volumetric video sequences. Our contribution is in four-fold: (1) The proposed voxel embedding generalizes the pixel embedding with 3D context information; (2) Present a simple multi-stream learning approach that allows effective spatial-temporal embedding; (3) Accomplished an end-toend framework for one-stage 3D cell instance segmentation and tracking without heavy parameter tuning; (4) The proposed 3D quantification is memory efficient via a single GPU with 12 GB memory. We evaluate our VoxelEmbed method on four 3D datasets (with different cell types) from the ISBI Cell Tracking Challenge. The proposed VoxelEmbed method achieved consistent superior overall performance (OP) on two densely annotated datasets. The performance is also competitive on two sparsely annotated cohorts with 20.6% and 2% of data-set having segmentation annotations. The results demonstrate that the VoxelEmbed method is a generalizable and memory-efficient solution.

show abstract

Section: Cosine Embedding Based Instance Segmentation and Trackingmentioning

confidence: 99%

VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning

Zhao¹,

Liu²,

Jha³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

ASIST: Annotation-free Synthetic Instance Segmentation and Tracking by Adversarial Simulations

Cited by 1 publication

References 43 publications

VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning

VoxelEmbed: 3D Instance Segmentation and Tracking with Voxel Embedding based Deep Learning

Contact Info

Product

Resources

About